# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

pip install lightgbm

pip list

import lightgbm as lgm
from sklearn.datasets import load_boston
import pandas as pd

X, y = load_boston(return_X_y=True)
bost = load_boston()
y_classification = (y>22.5).astype(int) # the objective of this line is to transform the target from continuous to binary 

#we load a train dataset
train = pd.DataFrame(X, columns = bost['feature_names'])

#we create a basic lightGBM model we'll be using for our exercieze:
X_train = lgm.Dataset(train, y_classification)
parameters = {
    "n_estimators": 3,
    "max_depth":3,
    "random_state": 43
}

#we train our model
basic_model = lgm.train(parameters,train_set = X_train)

#We create a contributions table
contributions = basic_model.predict(train, pred_contrib = True)
dataframe_contributions = pd.DataFrame(contributions, columns = list(bost['feature_names'])+["expected_value"]).drop(['expected_value'], axis = 1)